Graph-Enhanced Large Language Models for Spatial Search
It addresses the need for spatial reasoning in LLMs for domain-specific applications, but the approach is conceptual without concrete results.
The paper identifies spatial reasoning as a key weakness of LLMs and proposes integrating graph-based spatial data with LLMs to enable complex spatial question answering, aiming to improve performance in domains like urban planning and travel.
There have been many recent improvements in the ability of Large Language Models (LLMs) to perform complex tasks and answer domain-specific questions through techniques like Retrieval Augmented Generation (RAG). However, reasoning abilities of LLMs, including spatial reasoning abilities, are still lacking. Spatial reasoning is a key component required to answer questions in a variety of domains that are grounded in the physical world, including urban planning, civil engineering, travel, and many others. To advance the development of LLMs and facilitate an impact in these domains, new research techniques must be developed to enable LLMs to reason over spatial data, which is commonly stored in the form of a graph. In this paper we outline the challenges associated with spatial reasoning through LLMs and envision a future in which search engines integrate with LLMs to answer complex spatial questions through graph-enhanced reasoning.